chromegnomes:

the most frustrating thing about AI Art from a Discourse perspective is that the actual violation involved is pretty nebulous

like, the guys “laundering” specific artists’ styles through AI models to mimic them for profit know exactly what they’re doing, and it’s extremely gross

but we cannot establish “my work was scraped from the public internet and used as part of a dataset for teaching a program what a painting of a tree looks like, without anyone asking or paying me” as, legally, Theft with a capital T. not only is this DMCA Logic which would be a nightmare for 99% of artists if enforced to its conclusion, it’s not the right word for what’s happening

the actual Violation here is that previously, “I can post my artwork to share with others for free, with minimal risk” was a safe assumption, which created a pretty generous culture of sharing artwork online. most (noteworthy) potential abuses of this digital commons were straightforwardly plagiarism in a way anyone could understand

but the way that generative AI uses its training data is significantly more complicated - there is a clear violation of trust involved, and often malicious intent, but most of the common arguments used to describe this fall short and end up in worse territory

by which I mean, it’s hard to put forward an actual moral/legal solution unless you’re willing to argue:

it’s extremely annoying to talk about, because you’ll see people straight up gloating about their Intent To Plagiarize, but it’s hard to stick them with any specific crime beyond Generally Scummy Behavior unless you want to create some truly horrible precedents and usher in The Thousand Year Reign of Intellectual Property Law